Tio Moreno tiomoreno

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

Clojure Destructuring Tutorial and Cheat Sheet

(Related blog post)

Simply put, destructuring in Clojure is a way extract values from a datastructure and bind them to symbols, without having to explicitly traverse the datstructure. It allows for elegant and concise Clojure code.

Vectors and Sequences

Sample PHP+Mongo app on Heroku

Install any of the Mongo add-ons available at http://addons.heroku.com
Vendor the Mongo driver with your application. You can download it here:
```
https://github.com/wuputah/heroku-libraries/raw/master/php/mongo/mongo.so
```
Add it to a folder like "ext".

	#!/bin/bash

	set -x

	EMAIL=''
	API_KEY=''

	ZONE_ID=''
	RECORD_ID=''

	#!/usr/bin/env python


	# JS Minify
	# Python script that can process all JavaScript files in a directory
	# through the Closure compiler
	# original: http://taylanpince.com/blog/posts/automated-javascript-minification-with-fabric/

	import os
	from optparse import OptionParser